P-Net: A Representation for Partially-Sequenced, Multi-stream Activity

  • Yifan Shi
  • , Aaron F. Bobick

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, we devise a Propagation Net (P-Net) as a new mechanism for the representation and recognition of multi-stream activity. Most of daily activities can be represented by temporally partial ordered intervals where each interval has not only temporal constraint, i.e., before/after/duration, but also a logical relationship such as a and b both must happen. P-Net associates a node for each interval that is probabilistically triggered function dependent upon the state of its parent nodes. Each node is also associated with an observation distribution function that associates perceptual evidence. This evidence, generated by lower level vision modules, is a positive indicator of the elemental action. Using this architecture, we devise an iterative temporal sequencing algorithm that interprets a multi-dimensional observation sequence of visual evidence as a multi-stream propagation through the P-Net. Simple vision and motion-capture data experiments demonstrate the capabilities of our algorithm.

Original languageEnglish
Title of host publication2003 Conference on Computer Vision and Pattern Recognition Workshop, CVPRW 2003
PublisherIEEE Computer Society
Pages40-45
Number of pages6
ISBN (Electronic)0769519008
DOIs
StatePublished - 2003
EventConference on Computer Vision and Pattern Recognition Workshop, CVPRW 2003 - Madison, United States
Duration: Jun 16 2003Jun 22 2003

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume4
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Conference

ConferenceConference on Computer Vision and Pattern Recognition Workshop, CVPRW 2003
Country/TerritoryUnited States
CityMadison
Period06/16/0306/22/03

Keywords

  • Activity recognition
  • Bayesian network
  • finite
  • state machine
  • stochastic state propagation

Fingerprint

Dive into the research topics of 'P-Net: A Representation for Partially-Sequenced, Multi-stream Activity'. Together they form a unique fingerprint.

Cite this